Reasoning Fine-Tuning Induces Persistent Latent Policy States

• URL: http://arxiv.org/abs/2607.18532v1
• Date: Mon, 20 Jul 2026 21:56:22 GMT
• Title: Reasoning Fine-Tuning Induces Persistent Latent Policy States
• Abstract summary: We show that reasoning-fine-tuned models exhibit richer latent-policy organization than their base counterparts.<n>Our results suggest that reasoning fine-tuning globally reorganizes latent dynamics.
• Score: 1.0467550794914122
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly understood. It is unclear whether reasoning fine-tuning improves local token-level competence or globally reorganizes how models structure inference over time. We address this question by modeling Chain-of-Thought reasoning as a switching dynamical system (SDS), in which internal representations evolve under discrete latent policy states. Our framework combines time-aware contrastive representation learning with discrete regime discovery to recover latent policies from activation trajectories. Across four benchmarks and model scales from 1.5B to 32B parameters, reasoning-fine-tuned models exhibit richer latent-policy organization than their base counterparts, characterized by more differentiated transition structure and model-dependent changes in state utilization, persistence, and mixing. The recovered regimes exhibit functional specialization aligned with distinct reasoning stages, and extensive controls confirm that their structure is not explained by correctness, representation learning, or modeling priors, but depends on the coherent temporal organization of reasoning trajectories. Causal interventions further show that the regimes are functionally meaningful: state-swap ablations reduce one-step predictive fit, while transplanting reasoning dynamics into base models improves performance on challenging reasoning problems. Finally, SDS-guided pruning of failure-prone reasoning prefixes outperforms self-consistency in 11 of 12 model-dataset settings, with gains of up to 12.5 percentage points. Together, our results suggest that reasoning fine-tuning globally reorganizes latent dynamics, offering a new lens for mechanistic analysis and process-level control of reasoning models.

Related papers

• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• Learning Structured Reasoning via Tractable Trajectory Control [99.75278337895024]
  Ctrl-R is a framework for learning structured reasoning via tractable trajectory control.<n>We show that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns.
  arXiv  Detail & Related papers  (2026-03-02T09:18:19Z)
• Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models [50.39102836928242]
  We introduce a representational perspective to investigate the dynamics of the model's internal states.<n>We discover that post-training yields only limited improvement in static initial representation quality.
  arXiv  Detail & Related papers  (2026-01-31T15:23:33Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning [8.01259760303241]
  We investigate whether a partially completed reasoning chain can be reliably continued by another model.<n>We use token-level log-probability thresholds to truncate reasoning at early, mid, and late stages from our baseline models.<n>Our findings point towards interchangeability as an emerging behavioral property of reasoning models.
  arXiv  Detail & Related papers  (2025-12-16T02:56:44Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Latent Convergence Modulation in Large Language Models: A Novel Approach to Iterative Contextual Realignment [0.0]
  A structured modulation mechanism was introduced to regulate hidden state transitions.<n>Lattice adjustments contributed to reductions in perplexity fluctuations, entropy variance, and lexical instability.
  arXiv  Detail & Related papers  (2025-02-10T09:46:33Z)
• On the Reasoning Capacity of AI Models and How to Quantify It [0.0]
  Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities.<n>While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit limitations in more complex reasoning tasks.<n>We propose a novel phenomenological approach that goes beyond traditional accuracy metrics to probe the underlying mechanisms of model behavior.
  arXiv  Detail & Related papers  (2025-01-23T16:58:18Z)
• A NotSo Simple Way to Beat Simple Bench [0.0]
  This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs)<n>We propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness.<n>Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts.
  arXiv  Detail & Related papers  (2024-12-12T16:04:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.